← Back to community benchmarks
gemma-4-31B-it-oQ4
Performance
1k
tokens
676.3
PP tok/s
25.8
TG tok/s
1514
TTFT (ms)
18.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.12
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 676.3 | 25.8 | 18.1 GB | current |
| 64k | 493.5 | 15.1 | 28.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.8 | 1.00× |
| 2× | 40.6 | 1.57× |